Re: 8.3devel slower than 8.2 under read-only load
От | Simon Riggs |
---|---|
Тема | Re: 8.3devel slower than 8.2 under read-only load |
Дата | |
Msg-id | 1195723786.4246.125.camel@ebony.site обсуждение исходный текст |
Ответ на | Re: 8.3devel slower than 8.2 under read-only load ("Guillaume Smet" <guillaume.smet@gmail.com>) |
Ответы |
Re: 8.3devel slower than 8.2 under read-only load
|
Список | pgsql-hackers |
On Thu, 2007-11-22 at 00:30 +0100, Guillaume Smet wrote: > > Is the data identical on both systems? Guillaume, Sounds comprehensive, thanks for double checking. Would it be possible to do these tests? 1. Compare SELECT 1; This will allow us to remove planner and indexscan overheads from results, though will still include protocol and tcop stuff. 2. Compare SELECT ... WHERE values are constants This will cause the clients to reuse the plan already made, so should effectively remove planner, but not indexscan overheads from the test. 3. Change the test to look at Integers columns only for the WHERE clause, so we can remove any thought it has anything to do with text data, collation etc.. >From those tests we should be able to narrow things down to planner, executor or indexscan related. Thanks, -- Simon Riggs 2ndQuadrant http://www.2ndQuadrant.com
В списке pgsql-hackers по дате отправления: